[go: up one dir, main page]

WO2003039082A1 - Procede de communication d'un trafic de donnees temps reel dans un reseau de communication base sur la detection de collision, un moyen d'enregistrement correspondant et un reseau de communication - Google Patents

Procede de communication d'un trafic de donnees temps reel dans un reseau de communication base sur la detection de collision, un moyen d'enregistrement correspondant et un reseau de communication Download PDF

Info

Publication number
WO2003039082A1
WO2003039082A1 PCT/EP2002/011017 EP0211017W WO03039082A1 WO 2003039082 A1 WO2003039082 A1 WO 2003039082A1 EP 0211017 W EP0211017 W EP 0211017W WO 03039082 A1 WO03039082 A1 WO 03039082A1
Authority
WO
WIPO (PCT)
Prior art keywords
messages
message
real
scheduling
time data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/EP2002/011017
Other languages
German (de)
English (en)
Inventor
Ulrich Lauther
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens AG
Siemens Corp
Original Assignee
Siemens AG
Siemens Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens AG, Siemens Corp filed Critical Siemens AG
Priority to DE50202298T priority Critical patent/DE50202298D1/de
Priority to CA002465234A priority patent/CA2465234A1/fr
Priority to EP02802288A priority patent/EP1440544B1/fr
Priority to AT02802288T priority patent/ATE289463T1/de
Priority to US10/494,342 priority patent/US7489676B2/en
Publication of WO2003039082A1 publication Critical patent/WO2003039082A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/12—Shortest path evaluation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/64—Hybrid switching systems
    • H04L12/6418—Hybrid transport
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/64—Hybrid switching systems
    • H04L12/6418—Hybrid transport
    • H04L2012/6489—Buffer Management, Threshold setting, Scheduling, Shaping

Definitions

  • the invention relates to a method for communicating real-time data traffic in a collision detection-based communication network, for example the real-time Ethernet protocol, in which real-time data traffic takes place deterministically, for example predictably, over a conventional Ethernet network.
  • a collision detection-based communication network for example the real-time Ethernet protocol
  • Such a system is known, for example, from international patent application WO 00/03521, in which when real-time data are transmitted, a corresponding middleware between the application program and the Ethernet protocol prevents a data collision during real-time transmission.
  • this middleware must be present in every network node.
  • the object of the invention is to provide a method for communicating real-time data traffic in a collision detection-based communication network by means of a corresponding storage medium and a communication network, in each of which the disadvantages mentioned above are avoided.
  • the invention essentially relates to a method for a collision detection-based communication network, for example the Ethernet, in which real time data traffic is routed to the least expensive data paths before cyclically recurring real-time data traffic, and then the real-time data traffic messages are then scheduled with the help of a greedy heuristic (greedy heuristic) to enable cyclically recurring real-time data traffic without conflict and with the shortest possible cycle time.
  • a greedy heuristic greedy heuristic
  • FIG. 2 shows a condition graph when a message is transmitted in broadcast mode
  • FIG. 3 shows a condition graph when a message is duplicated
  • FIG. 4 shows a gant diagram for the case of FIG. 2,
  • FIG. 5 shows a gant diagram for the case of FIG. 3,
  • FIG. 6 shows a condition graph with a duplicated message
  • FIG. 7 shows a solution for the case of FIG. 6 in the form of a gantt diagram
  • FIG. 8 shows a simple ring topology to explain the redundancy treatment
  • FIG. 9 shows a gantt diagram with two independently routed messages for the case of FIGS. 8 and
  • FIG. 10 shows two messages routed in the resource disjoint mode for the case of FIG. 8.
  • the communication cycle is split into a real-time part, which contains these planned messages, and a non-real-time part, in which the unplanned transactions take place using standard TCP / UDP / IP methods.
  • the real-time part should take up as little space as possible in the overall cycle in order to keep a sufficiently large space for unplanned transactions.
  • the network consists of switching units (switches) and bidirectional connections (links). Each link connects a pair of switches, or more specifically, ports from these two switches.
  • the links cause delays that are proportional to the length of the links.
  • fixed delay times for the transmission of a message by a switch are assumed; this delay thus subsumes the admission of a synchronization jitter, which is not considered further in the scheduling.
  • the network topology is typically ring-like or tree-like, but is not limited to these simple topologies.
  • routing and scheduling are not independent tasks; the selection made in the routing phase influences the quality of the scheduling. In a simpler variant of the invention, however, the routing and scheduling are considered to be independent of one another.
  • a network description and a list of messages serve as the input variable for the routing. For every message the sending switch and a lot of receiving switches are known.
  • the routing task now consists of finding a path, i.e. a set of switches or their ports, in order to pass the message on to the destination. If a message has k destinations, the sender can send it to all recipients at the same time, branching it to intermediate switches (broadcast mode), or it can be sent to the k recipients at k different times regardless of the sender. the. In addition, variations between these two extremes are of course also possible. It becomes clear below that the choice between these options is not trivial and can take place within the scheduling. As a result of the routing, the links and ports and the relative arrival times are then determined for each message relative to the time of transmission, the arrival times being able to be calculated in a simple manner on the sum of the delays through the links and switches that a message passes.
  • the task of scheduling is to assign absolute times for the messages sent in such a way that there are no conflicts between the messages and that the total cycle time for the transmission of all messages (make span) is minimized. Due to the conditions given by the routing, the arrival times at all ports that are used by the messages are also automatically determined.
  • Resource conflicts at port inputs do not need to be considered if the conflicts at the port outputs of the scheduling are resolved. If such two messages do not follow one another immediately, the gaps between the two messages must of course also be taken into account during scheduling.
  • the task of scheduling is therefore to assign each message to one or more transmission times in such a way that all inequalities are met and the total time for the transmission of the messages is minimized.
  • MessPort describes a passed through to a port
  • Message and includes the relative time of arrival of the message on the port, a pointer to the message and a pointer to the port.
  • Port describes a port and points to the associated switch and the associated link.
  • the data structure includes a list of measurement ports to access all
  • Switch describes a switch and contains the name of the switch and pointers to its ports.
  • Link describes a link and contains the length or delay of the link as well as pointers to the two ports that are connected by this link.
  • Message describes a message and contains the
  • the list of measurement ports is the result of the routing phase and the times the result of the scheduling phase.
  • Constraint describes a condition between the scheduling times of two messages, as shown, for example, by the inequalities given above.
  • Component describes a connected part of a
  • Constraint graph contains a list of all messages and ports belonging to the respective component.
  • the network is modeled by a graph for routing.
  • a graph for routing There are a number of ways to do this, but it is sufficient to model a switch as a node and a link as an edge of a routing graph. Since all links are bidirectional, an undirected graph from the TURBO-C ++ class library can be used, for example.
  • the Dijkstra algorithm which is well known from the literature, can be used to form the shortest path tree for each message, starting from the switch sending the respective message. For reasons of efficiency, the priority queue required by the Dijkstra algorithm is used for those with labels provided but not yet treated nodes implemented as a so-called radix queue. The tree creation process is stopped when all target nodes or receiving switches have a permanent label.
  • the shortest path from the target node back to the root node of the tree can easily be traced, with MessPort- Objects are created and added to the MessPort list of the corresponding message and port.
  • the main result of the routing are the MessPort objects that are contained in the port and message objects. This provides easy access to all messages that pass through a particular port and to all ports that are passed through by any given message.
  • the scheduling conditions specified above can also be modeled, for example, by an undirected graph, the nodes of the graph corresponding to messages and the edges corresponding to conditions that must be met when the times are assigned to the two messages. In this way, however, a large number of "parallel" conditions arise, of which only the strongest of these conditions are relevant for scheduling.
  • the conditions can either be stored explicitly in the graph for the conditions, for example in a matrix, in order to obtain quick access for a respective pair of nodes, or they can also be represented implicitly and only be generated if ports that are connected by a certain message used to be examined. Processing time can be saved here if the scheduling problem is broken down into smaller sub-problems that can be solved independently of one another. This works if there are no direct or indirect conditions between messages.
  • a lower bound is determined for evaluating the heuristics for the scheduling in order to have an estimate of the distance from the optimum.
  • This lower bound can be formed, for example, on the basis of messages that use a specific port, for each port all message lengths are added up and the maximum is formed from them and represents a lower bound for the entire cycle time (make span).
  • maximum subsets of messages between which conditions exist in pairs that is, maximum groups (cliques) in the condition graph, can also be used.
  • grey heuristics For the actual scheduling, "greedy" heuristics (greedy heuristics) are used, messages being allocated using a priority scheme after the shortest execution time. After scheduling has been carried out for a message, the lowest execution time is reassigned for all messages not yet planned by the scheduling and their priorities (updating).
  • the MessPort objects are deleted from their list in the port, so that there is no longer an update for the messages for which scheduling has already been carried out. In this way, the number of MessPort objects decreases as the scheduling progresses until the lists are then renewed in a last step.
  • improvement () ⁇ while (solution can be improved) ⁇ select a message m and remove it from the schedule; find best position to reinsert m into the schedule; reinsert m into the schedule; ⁇
  • a longest path concept is required for this purpose. After the scheduling, the originally undirected condition graph is directed; each edge is directed from the later scheduled message to the earlier scheduled message. The length of the longest path in the graph, from any node or message to any sink of the graph, gives the earliest execution time for the scheduling of the respective message. Tracing back the edges of the graph and calculating the longest path gives the latest execution time, unless the total cycle time is increased. If the latest execution time is greater than the earliest execution time, the message has a so-called slip (slack). Removing this slip-prone message cannot reduce the overall cycle time.
  • Finding the best position can be done by simply going through the messages in the order they are scheduled by the scheduling. Finding the best position can be described, for example, by the following pseudo code:
  • FIG. 1 the handling of messages with multiple destinations is demonstrated using a small example with three messages M1, M2 and M3 and four switching devices A ... D.
  • a first port A (l) of switch A is connected to a first port B (l) of switch B
  • a second port B (2) of this switch is connected to a first port C (l) of switch C
  • a third port B ( 3) of switch B connected to a first port D (l) of switch D.
  • the message M1 is to be transmitted from switch B to switches C and D, the message M2 from switch A to switch C and the message M3 from switch A to switch D.
  • the ports are plotted in so-called Gantt diagrams over a horizontal time axis in the vertical direction and the port assignment by the messages is represented by rectangles, messages with diagonal lines through them being slippery.
  • the respective large rectangle below the ports shows the respective lower time limit for the scheduling.
  • Messages with more than one destination can therefore be handled in different ways. By breaking up a message in partial messages that are handled independently, additional data traffic is generated, which, however, can possibly increase the total cycle time. On the other hand, if the message is routed tree-like, ie if it is only sent once from the origin, this can lead to more difficult conditions to be met. Routing and scheduling must be modified to find the best compromise between generating too much data traffic or overly constrained problems. Routing messages for multiple recipients must be handled in two different ways.
  • the message has a "broadcast" flag, no special action is necessary, since it is easy to exclude common partial paths when tracing back. If the broadcast mode is not required for multi-recipient messages, the message can also be sent several times. In this case, after the routing of the message, a separate message object is generated for each receiving switch, all messages in this group being given a single common identification, so that the scheduling can continue to handle the messages in this group in a special way. If after the routing the MessPorts of such a partial message _ a subset of the others
  • the duplication of messages creates scheduling problems with fewer conditions, but leads to additional data traffic, which can be partially eliminated in the scheduling phase.
  • the duplication of messages can also take place before routing, which leads to greater freedom in routing. Doubling only after routing, however, ensures that all partial messages of a duplication group that pass through a certain given port have the same relative arrival time at this port, which in turn makes it easier to recombine the partial messages in the scheduling phase.
  • scheduling partial messages that originate from the same message are handled in a special way. These messages are allowed to be scheduled at identical times by the scheduling. Therefore, conditions between partial messages that are generated from a single original message must be taken into account accordingly. A pair of such messages can be scheduled either under normal conditions or at identical times through the scheduling.
  • An example of this technique is shown in 6 and shows the conditions for the example given above when message M3 is deleted. It can be seen from the corresponding Gantt diagram in FIG. 7 that the messages M1 and M1 are now scheduled at the same time.
  • sequences of neighboring sub-messages that originate from a single original message are given priority over other messages. These neighboring sub-messages are then merged again if this is possible without increasing the total cycle time.
  • the combination is carried out by concatenation of the lists of MessPorts, of the two messages with deletion of the duplicates in the resulting list and deletion of one of the two messages.
  • This ring topology consists of switches A, B and C, with the
  • Port A (l) are connected to port B (l), port B (2) to port C (l) and port A (2) to port C (4) and where messages Ml and M2 are each from Switch A can be transferred to Switch C.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Traffic Control Systems (AREA)

Abstract

L'invention concerne principalement un procédé destiné à un réseau de communication basé sur la détection de collision, par exemple, l'Ethernet. Selon ce procédé, chronologiquement avant un trafic de données temps réel à répétition cyclique, un acheminement du trafic de données temps réel s'effectue sur le chemin de données le plus économique puis un ordonnancement des messages du trafic de données temps réel s'effectue à l'aide d'une heuristique gloutonne (Greedy Heuristic) pour permettre un trafic de données temps réel à répétition cyclique sans conflit et avec un temps de cycle le plus court possible.
PCT/EP2002/011017 2001-10-31 2002-10-01 Procede de communication d'un trafic de donnees temps reel dans un reseau de communication base sur la detection de collision, un moyen d'enregistrement correspondant et un reseau de communication Ceased WO2003039082A1 (fr)

Priority Applications (5)

Application Number Priority Date Filing Date Title
DE50202298T DE50202298D1 (de) 2001-10-31 2002-10-01 Verfahren zur kommunikation eines realzeit-datenverkehrs in einem kollisionserkennungs-basierten kommunikationsnetz, entsprechendes speichermedium und kommunikationsnetz
CA002465234A CA2465234A1 (fr) 2001-10-31 2002-10-01 Procede de communication d'un trafic de donnees temps reel dans un reseau de communication base sur la detection de collision, un moyen d'enregistrement correspondant et un reseaude communication
EP02802288A EP1440544B1 (fr) 2001-10-31 2002-10-01 Procede de communication d' un trafic de donnees temps reel dans un reseau de communication base sur la detection de collision, support d'enregistrement correspendant et reseau de communication
AT02802288T ATE289463T1 (de) 2001-10-31 2002-10-01 Verfahren zur kommunikation eines realzeit- datenverkehrs in einem kollisionserkennungs- basierten kommunikationsnetz, entsprechendes speichermedium und kommunikationsnetz
US10/494,342 US7489676B2 (en) 2001-10-31 2002-10-01 Communication method of exchanging real-time data in a collision recognition-based communication network, corresponding memory medium and communication network

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP01126052 2001-10-31
EP01126052.8 2001-10-31

Publications (1)

Publication Number Publication Date
WO2003039082A1 true WO2003039082A1 (fr) 2003-05-08

Family

ID=8179143

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2002/011017 Ceased WO2003039082A1 (fr) 2001-10-31 2002-10-01 Procede de communication d'un trafic de donnees temps reel dans un reseau de communication base sur la detection de collision, un moyen d'enregistrement correspondant et un reseau de communication

Country Status (8)

Country Link
US (1) US7489676B2 (fr)
EP (1) EP1440544B1 (fr)
CN (1) CN100450071C (fr)
AT (1) ATE289463T1 (fr)
CA (1) CA2465234A1 (fr)
DE (1) DE50202298D1 (fr)
ES (1) ES2233878T3 (fr)
WO (1) WO2003039082A1 (fr)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007014856A1 (fr) * 2005-08-01 2007-02-08 Siemens Aktiengesellschaft Procede d'ordonnancement du flux de donnees dans des reseaux commutes, lie a des phases
WO2007031006A1 (fr) * 2005-09-13 2007-03-22 Zte Corporation Procede de commutation virtuelle qui peut etre acheminee
US7750160B2 (en) 2003-11-13 2010-07-06 Ambit Biosciences Corporation Isoxazolyl urea derivatives as kinase modulators
US7797425B2 (en) 2005-12-22 2010-09-14 Amdocs Systems Limited Method, system and apparatus for communications circuit design

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011076081A1 (fr) * 2009-12-23 2011-06-30 Lin Dingwei Système de commande de fonctionnement automatique de réseau logique, système de commande d'automatisation et procédé d'application
CN101908988B (zh) * 2010-08-06 2011-11-09 北京交大资产经营有限公司 实时以太网系统及其实现方法
CN117288181B (zh) * 2023-11-27 2024-02-02 中国电子科技集团公司第十研究所 一种导航源选择方法及装置

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1009189A2 (fr) * 1998-12-08 2000-06-14 Nec Corporation Planification RRGS-round-robin cupide pour commutateurs térabit aux tampons d'entrée et sortie
US6101188A (en) * 1996-09-12 2000-08-08 Nec Corporation Internetworking router
US20010002195A1 (en) * 1998-08-19 2001-05-31 Path 1 Network Technologies, Inc., California Corporation Methods and apparatus for providing quality-of-service guarantees in computer networks

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2803262B2 (ja) * 1989-12-15 1998-09-24 日本電気株式会社 パケット・スイッチ
US5842173A (en) * 1994-10-14 1998-11-24 Strum; David P. Computer-based surgical services management system
US6189022B1 (en) * 1997-08-20 2001-02-13 Honeywell International Inc. Slack scheduling for improved response times of period transformed processes
US6483846B1 (en) 1998-07-10 2002-11-19 Honeywell Inc. Middleware-based real-time communication system
US6418139B1 (en) * 1998-11-25 2002-07-09 Nortel Networks Limited Mechanism to guarantee quality of service to real-time traffic on IP networks
US7145869B1 (en) * 1999-03-17 2006-12-05 Broadcom Corporation Method for avoiding out-of-ordering of frames in a network switch
US6891834B1 (en) * 1999-09-09 2005-05-10 Avici Systems Apparatus and method for packet scheduling
US6882625B2 (en) * 2000-12-14 2005-04-19 Nokia Networks Oy Method for scheduling packetized data traffic

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6101188A (en) * 1996-09-12 2000-08-08 Nec Corporation Internetworking router
US20010002195A1 (en) * 1998-08-19 2001-05-31 Path 1 Network Technologies, Inc., California Corporation Methods and apparatus for providing quality-of-service guarantees in computer networks
EP1009189A2 (fr) * 1998-12-08 2000-06-14 Nec Corporation Planification RRGS-round-robin cupide pour commutateurs térabit aux tampons d'entrée et sortie

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7750160B2 (en) 2003-11-13 2010-07-06 Ambit Biosciences Corporation Isoxazolyl urea derivatives as kinase modulators
WO2007014856A1 (fr) * 2005-08-01 2007-02-08 Siemens Aktiengesellschaft Procede d'ordonnancement du flux de donnees dans des reseaux commutes, lie a des phases
DE102005036064A1 (de) * 2005-08-01 2007-02-15 Siemens Ag Verfahren zum phasenbezogenen Scheduling des Datenflusses in geschalteten Netzwerken
DE102005036064B4 (de) * 2005-08-01 2007-07-19 Siemens Ag Verfahren zum phasenbezogenen Scheduling des Datenflusses in geschalteten Netzwerken
US8005111B2 (en) 2005-08-01 2011-08-23 Siemens Aktiengesellschaft Method for the phase-related scheduling of data flow in switched networks
WO2007031006A1 (fr) * 2005-09-13 2007-03-22 Zte Corporation Procede de commutation virtuelle qui peut etre acheminee
CN100373892C (zh) * 2005-09-13 2008-03-05 中兴通讯股份有限公司 一种可路由的虚交换方法
US7797425B2 (en) 2005-12-22 2010-09-14 Amdocs Systems Limited Method, system and apparatus for communications circuit design

Also Published As

Publication number Publication date
ES2233878T3 (es) 2005-06-16
CN1582554A (zh) 2005-02-16
CA2465234A1 (fr) 2003-05-08
CN100450071C (zh) 2009-01-07
DE50202298D1 (de) 2005-03-24
EP1440544A1 (fr) 2004-07-28
US7489676B2 (en) 2009-02-10
US20050002413A1 (en) 2005-01-06
EP1440544B1 (fr) 2005-02-16
ATE289463T1 (de) 2005-03-15

Similar Documents

Publication Publication Date Title
DE69429983T2 (de) Datenübertragungsnetz und Verfahren zum Betreiben des Netzes
DE4430993C1 (de) Verfahren zur adaptiven Wegesuche in einem Kommunikationsnetz
DE69909791T2 (de) Verteilte rechnerumgebung mit echt-zeit ablauffolgenlogik und zeit-deterministischer architektur
DE69533230T2 (de) Verfahren und vorrichtung zur verbesserung der fehlertoleranz eines netzwerkes
DE3888818T2 (de) Aufgeteilte Lastverteilung.
DE3855925T2 (de) Nachrichtenübertragung in einem multiplexsystem
DE69034133T2 (de) Kommunikationsgerät
DE69132633T2 (de) Verfahren und Gerät zur Entfernungsvektorlenkung in Punkt-zu-Punkt Datagram Verbindungen
DE69032466T2 (de) Aktualisierung von Verbindungszustandsinformationen in Netzwerken
DE68918275T2 (de) Schnelles, digitales Paketvermittlungssystem.
DE69029082T2 (de) Verfahren zum Suchen von alternierenden Wegen in einem Kommunikationsnetz
DE3685599T2 (de) Vermittlungssystem fuer datenuebertragung.
DE3619906A1 (de) Adaptives uebermittlungssystem
DE19531749A1 (de) Verkehrsgestaltungseinrichtung und Paket-Kommunikationsgerät
EP0329005B1 (fr) Procédé pour l'établissement de circuits virtuels à travers les commutateurs d'un dispositif de commutation à plusieurs étages
DE3044792A1 (de) Elektronisches multiprozessor-system zur behandlung digitaler und analoger daten
DE3305115A1 (de) Uebertragungsnetzwerk
DE69837609T2 (de) Kommunikationsnetz
DE2731200A1 (de) Anordnung zum steuern von datenfluessen
DE10052904B4 (de) Warteschlangenbildungsverfahren zur Weiterleitung von Paketen in Folge
EP1440544B1 (fr) Procede de communication d' un trafic de donnees temps reel dans un reseau de communication base sur la detection de collision, support d'enregistrement correspendant et reseau de communication
DE112019007400T5 (de) Verfahren zur Verifizierung eines Interrupt-Antriebssystems basierend auf einem Interrupt-Sequenzdiagramm
DE3882380T2 (de) Übertragungssysteme und vermittlungselement zur verwendung darin.
DE102005036064B4 (de) Verfahren zum phasenbezogenen Scheduling des Datenflusses in geschalteten Netzwerken
DE60205777T2 (de) Effiziente behandlung von zeitüberschreitungsnachrichten in einem seriellen ieee 1394 bus netzwerk mit busbrücken

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NO NZ OM PH PL PT RO RU SD SE SG SI SK SL TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR IE IT LU MC NL PT SE SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
WWE Wipo information: entry into national phase

Ref document number: 2002802288

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2465234

Country of ref document: CA

WWE Wipo information: entry into national phase

Ref document number: 2002821823X

Country of ref document: CN

Ref document number: 10494342

Country of ref document: US

WWP Wipo information: published in national office

Ref document number: 2002802288

Country of ref document: EP

REG Reference to national code

Ref country code: DE

Ref legal event code: 8642

WWG Wipo information: grant in national office

Ref document number: 2002802288

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: JP

WWW Wipo information: withdrawn in national office

Country of ref document: JP